translate-voice-message
Skill0 starsChanged 16 days agoMITView on GitHub
Translate a voice message or audio recording into another language and voice it in the same speaker's voice, with the VocaLingo MCP server. Returns the transcript, the translation and an audio file. Use when the user wants to hear a voice note in their language, reply to someone in a language they don't speak, or translate speech while keeping the voice.
In this repository7 other files it gives its agents.
- add-subtitlesSkill
- change-voiceSkill
- dub-videoSkill
- speak-in-your-voiceSkill
- summarize-videoSkill
- transcribe-audioSkill
- translate-imageSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Call translate_audio { source, targetLanguage }.
- Very specific: line 20
If the user only needs to understand what was said, speech_to_text plus your own translation is cheaper.
- Very specific: line 39
Every error has a code and a nextStep: follow nextStep.
- Very specific: line 43
If no VocaLingo tools are available, the server is not connected yet.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Translate a voice message keeping the voice
Works through the VocaLingo MCP server (https://nodejs.vocalingo.app/mcp). Tools: translate_audio, speech_to_text, list_voices, check_job, get_upload_url.
Steps
- Get the source: a direct file link or a
fileIdafter upload (see "Files" below). Files up to 150 MB. - Call
translate_audio { source, targetLanguage }. Languages take an ISO code (es) or a name (Spanish,Español).voicedefaults to"clone": a one-off copy of the speaker's voice from this recording. Nothing is saved.voice: "none"returns text only.- A
voiceIdfromlist_voicesvoices the translation with that saved voice (for example, the user's own voice for a reply).
- Usually the result comes back in the same call:
transcript,translatedText,summary,translatedAudioUrl. Otherwise you get ajobId: callcheck_job { jobId }with the same id until it finishes. - Give the user the audio link and the translated text.
If the user only needs to understand what was said, speech_to_text plus your own translation is cheaper.
Cost
About 2 to 3 VocaLingo tokens per minute for target languages en, ru, zh, de, fr, es, it, ja, ko, pt (needs 3+ seconds of speech). Other target languages use another voice engine: about 180 tokens extra and at least 10 seconds of speech, so the call returns confirmation_required first.
Files
- Public link: pass it as
source. - Agent with a shell (Claude Code, Cursor, Codex, Gemini CLI): call
get_upload_url { filename }, run the returnedcurlCommandwith the local path, then pass thefileIdassource. AfileIdstays valid for 48 hours, so reuse it instead of uploading again. - Chat app (claude.ai, Claude apps): call
get_upload_urland the user gets an upload button in the chat (if there is no button, give thembrowserUploadUrl). Wait for their message with thefileId. Do not upload from a code sandbox: its network blocks the upload domain. - ChatGPT: a file attached to the message reaches the tool through its
fileparameter, no upload step needed.
Tokens and confirmation
Tools spend VocaLingo tokens, the currency of the user's VocaLingo account (unrelated to LLM tokens). A call that would cost 50 tokens or more does not start: it returns status: "confirmation_required" with the price and a confirmToken. Show the price and ask. Only after the user agrees, repeat the same call with confirmToken added. Never confirm on the user's behalf. dryRun: true returns the estimate without starting anything. On insufficient_balance, tell the user to top up in the VocaLingo app and stop.
Errors
Every error has a code and a nextStep: follow nextStep. If the same call fails twice, show the error to the user and stop.
Not connected
If no VocaLingo tools are available, the server is not connected yet. Send the user to https://github.com/umakhanpro/vocalingo-mcp#connect. They need a VocaLingo account (https://vocalingo.app) and sign in through the browser.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

